Plurals：一种通过模拟社会集成引导大语言模型的系统
Plurals: A System for Guiding LLMs Via Simulated Social Ensembles
AI总结：
针对大语言模型可能存在观点偏向的问题，研究提出Plurals多元AI审议系统，通过模拟社会集成实现多视角审议，经案例与实验验证其理论契合度与实用效果，提供开源Python库。
摘要：
近期的讨论引发了人们对语言模型可能偏向特定观点的担忧。但如果解决方案并非追求“无立场视角”，而是利用不同的观点呢？我们推出Plurals，一个用于多元主义AI审议的系统及Python库。Plurals由在可定制结构中开展审议的智能体（大语言模型，可配备人物设定）组成，并有主持人监督审议过程，它是一种模拟社会集成生成器。Plurals可对接政府数据集以生成具有全国代表性的人物设定，包含受协商民主启发的审议模板，还支持用户自定义结构内的信息共享机制与审议行为。6项案例研究证明了其对理论构念的契合度与有效性。3项随机实验显示，模拟焦点小组生成的内容能引发相关受众在线样本的共鸣（在75%的试验中，其表现优于零样本生成结果）。Plurals既是多元主义AI的一种范式，也是一套具体系统。Plurals库可在https://github.com/josh-ashkinaze/plurals获取，并将持续更新。
英文摘要：
Recent debates raised concerns that language models may favor certain viewpoints. But what if the solution is not to aim for a 'view from nowhere' but rather to leverage different viewpoints? We introduce Plurals, a system and Python library for pluralistic AI deliberation. Plurals consists of Agents (LLMs, optionally with personas) which deliberate within customizable Structures, with Moderators overseeing deliberation. Plurals is a generator of simulated social ensembles. Plurals integrates with government datasets to create nationally representative personas, includes deliberation templates inspired by deliberative democracy, and allows users to customize both information-sharing structures and deliberation behavior within Structures. Six case studies demonstrate fidelity to theoretical constructs and efficacy. Three randomized experiments show simulated focus groups produced output resonant with an online sample of the relevant audiences (chosen over zero-shot generation in 75% of trials). Plurals is both a paradigm and a concrete system for pluralistic AI. The Plurals library is available at https://github.com/josh-ashkinaze/plurals and will be continually updated.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
